大家好，又见面了，我是你们的朋友全栈君。

博主将整个实战做成了视频讲解，视频链接：https://www.bilibili.com/video/BV16g4y1z7Qu/

实战流程

• 获得数据，并将数据处理成合适的格式
• 按照自己的设计搭建神经网络
• 设定合适的参数训练神经网络
• 在测试集上评价训练效果

一、认识mnist数据集

from keras.utils import to_categorical
from keras import models, layers, regularizers
from keras.optimizers import RMSprop
from keras.datasets import mnist
import matplotlib.pyplot as plt

# 加载数据集
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
print(train_images.shape, test_images.shape)
print(train_images[0])
print(train_labels[0])
plt.imshow(train_images[0])
plt.show()

将图片由二维铺开成一维

train_images = train_images.reshape((60000, 28*28)).astype('float')
test_images = test_images.reshape((10000, 28*28)).astype('float')
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

二、搭建一个神经网络

network = models.Sequential()
network.add(layers.Dense(units=15, activation='relu', input_shape=(28*28, ),))
network.add(layers.Dense(units=10, activation='softmax'))

三、神经网络训练

1、编译：确定优化器和损失函数等

# 编译步骤
network.compile(optimizer=RMSprop(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])

2、训练网络：确定训练的数据、训练的轮数和每次训练的样本数等

# 训练网络，用fit函数, epochs表示训练多少个回合， batch_size表示每次训练给多大的数据
network.fit(train_images, train_labels, epochs=20, batch_size=128, verbose=2)

四、用训练好的模型进行预测，并在测试集上做出评价

# 来在测试集上测试一下模型的性能吧
y_pre = network.predict(test_images[:5])
print(y_pre, test_labels[:5])
test_loss, test_accuracy = network.evaluate(test_images, test_labels)
print("test_loss:", test_loss, " test_accuracy:", test_accuracy)

五、完整代码

1、使用全连接神经网络

from keras.utils import to_categorical
from keras import models, layers, regularizers
from keras.optimizers import RMSprop
from keras.datasets import mnist
import matplotlib.pyplot as plt

# 加载数据集
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

train_images = train_images.reshape((60000, 28*28)).astype('float')
test_images = test_images.reshape((10000, 28*28)).astype('float')
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

network = models.Sequential()
network.add(layers.Dense(units=128, activation='relu', input_shape=(28*28, ),
                         kernel_regularizer=regularizers.l1(0.0001)))
network.add(layers.Dropout(0.01))
network.add(layers.Dense(units=32, activation='relu',
                         kernel_regularizer=regularizers.l1(0.0001)))
network.add(layers.Dropout(0.01))
network.add(layers.Dense(units=10, activation='softmax'))

# 编译步骤
network.compile(optimizer=RMSprop(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])

# 训练网络，用fit函数, epochs表示训练多少个回合， batch_size表示每次训练给多大的数据
network.fit(train_images, train_labels, epochs=20, batch_size=128, verbose=2)

# 来在测试集上测试一下模型的性能吧
test_loss, test_accuracy = network.evaluate(test_images, test_labels)
print("test_loss:", test_loss, " test_accuracy:", test_accuracy)

2、使用卷积神经网络

from keras.utils import to_categorical
from keras import models, layers
from keras.optimizers import RMSprop
from keras.datasets import mnist
# 加载数据集
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

# 搭建LeNet网络
def LeNet():
    network = models.Sequential()
    network.add(layers.Conv2D(filters=6, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
    network.add(layers.AveragePooling2D((2, 2)))
    network.add(layers.Conv2D(filters=16, kernel_size=(3, 3), activation='relu'))
    network.add(layers.AveragePooling2D((2, 2)))
    network.add(layers.Conv2D(filters=120, kernel_size=(3, 3), activation='relu'))
    network.add(layers.Flatten())
    network.add(layers.Dense(84, activation='relu'))
    network.add(layers.Dense(10, activation='softmax'))
    return network
network = LeNet()
network.compile(optimizer=RMSprop(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])

train_images = train_images.reshape((60000, 28, 28, 1)).astype('float') / 255
test_images = test_images.reshape((10000, 28, 28, 1)).astype('float') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

# 训练网络，用fit函数, epochs表示训练多少个回合， batch_size表示每次训练给多大的数据
network.fit(train_images, train_labels, epochs=10, batch_size=128, verbose=2)
test_loss, test_accuracy = network.evaluate(test_images, test_labels)
print("test_loss:", test_loss, " test_accuracy:", test_accuracy)